15 citations · 40 across the 9 of their papers we have counts for
3 papers · 1 filter
Learning to Limit Data Collection via Scaling Laws: A Computational Interpretation for the Legal Principle of Data Minimization
Divya Shanmugam, Samira Shabanian, Fernando Diaz +2
Modern machine learning systems are increasingly characterized by extensive personal data collection, despite the diminishing returns and increasing societal costs of such practice…
On the Learning Dynamics of Deep Neural Networks
Remi Tachet, Mohammad Pezeshki, Samira Shabanian +2
While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study t…
Bidirectional Helmholtz Machines
Jorg Bornschein, Samira Shabanian, Asja Fischer +1
Efficient unsupervised training and inference in deep generative models remains a challenging problem. One basic approach, called Helmholtz machine, involves training a top-down di…